Skill

select

Evaluate algorithms and full-stack technology options per sub-problem and application layer

Install

npx claudepluginhub jobrien127/plugin-marketplace --plugin solution-engine

Tool Access

This skill is limited to using the following tools:

Read Glob Grep Write WebSearch WebFetch Agent

Preview

For each sub-problem: select the algorithm. For each application layer: evaluate technology candidates.

SKILL.md

Similar Skills

cache-components

Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.

cache-components

139.2k

mcp-builder

9 files

Guides building MCP servers enabling LLMs to interact with external services via tools. Covers best practices, TypeScript/Node (MCP SDK), Python (FastMCP).

anthropics-skills-13

124.2k

canvas-design

20 files

Generates original PNG/PDF visual art via design philosophy manifestos for posters, graphics, and static designs on user request.

anthropics-skills-13

124.2k

Stats

Parent Repo Stars0

Parent Repo Forks0

Last CommitApr 24, 2026

Actions

View Source View Plugin View on GitHub View README

/select

For each sub-problem: select the algorithm. For each application layer: evaluate technology candidates.

Pipeline Position

Requires: decompose complete

Produces: $PROBLEMS_ROOT/$ARGUMENTS/stack/evaluation.md

Advances: select → complete

Instructions

Load $MATH_ROOT/optimization/06-sub-problems.md — the decomposed sub-problems.

Load ${CLAUDE_PLUGIN_ROOT}/templates/algorithm-catalog.yaml — candidate algorithms.

Load $PROBLEMS_ROOT/$ARGUMENTS/problem-state.yaml — scale, requirements, hosting.

For each sub-problem: a. Look up problem class in catalog b. Filter by scale ceiling and constraints c. If multiple candidates: rank by optimality × implementation simplicity d. Output: selected algorithm + rationale + scale switch threshold e. If problem class not in catalog: use judgment, flag uncertainty, add to catalog

For each application layer (see plan): a. Evaluate candidates against criteria (self-hostable, performant, maintainable, energy-efficient, LLM-toolable, operational complexity, cost at scale) b. Score each candidate 1-5 per criterion c. Output: scored table + recommendation

Write stack/evaluation.md.

Update pipeline-state.json.

/select

For each sub-problem: select the algorithm. For each application layer: evaluate technology candidates.

Pipeline Position

Requires: decompose complete
Produces: $PROBLEMS_ROOT/$ARGUMENTS/stack/evaluation.md
Advances: select → complete

Instructions

Load $MATH_ROOT/optimization/06-sub-problems.md — the decomposed sub-problems.
Load ${CLAUDE_PLUGIN_ROOT}/templates/algorithm-catalog.yaml — candidate algorithms.
Load $PROBLEMS_ROOT/$ARGUMENTS/problem-state.yaml — scale, requirements, hosting.
For each sub-problem: a. Look up problem class in catalog b. Filter by scale ceiling and constraints c. If multiple candidates: rank by optimality × implementation simplicity d. Output: selected algorithm + rationale + scale switch threshold e. If problem class not in catalog: use judgment, flag uncertainty, add to catalog
For each application layer (see plan): a. Evaluate candidates against criteria (self-hostable, performant, maintainable, energy-efficient, LLM-toolable, operational complexity, cost at scale) b. Score each candidate 1-5 per criterion c. Output: scored table + recommendation
Write stack/evaluation.md.
Update pipeline-state.json.